diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 20:15:43 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 20:15:43 +0300 |
commit | 08cdc2157966c07d3f986a097ddaa74cee312751 (patch) | |
tree | dad2562768b49876c642c2505813e90a467ae40a /drivers/vfio/vfio.h | |
parent | aa5ad10f6cca6d42f3fef6cb862e03b220ea19a6 (diff) | |
parent | d6c55c0a20e5059abdde81713ddf6324a946eb3c (diff) | |
download | linux-08cdc2157966c07d3f986a097ddaa74cee312751.tar.xz |
Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd
Pull iommufd implementation from Jason Gunthorpe:
"iommufd is the user API to control the IOMMU subsystem as it relates
to managing IO page tables that point at user space memory.
It takes over from drivers/vfio/vfio_iommu_type1.c (aka the VFIO
container) which is the VFIO specific interface for a similar idea.
We see a broad need for extended features, some being highly IOMMU
device specific:
- Binding iommu_domain's to PASID/SSID
- Userspace IO page tables, for ARM, x86 and S390
- Kernel bypassed invalidation of user page tables
- Re-use of the KVM page table in the IOMMU
- Dirty page tracking in the IOMMU
- Runtime Increase/Decrease of IOPTE size
- PRI support with faults resolved in userspace
Many of these HW features exist to support VM use cases - for instance
the combination of PASID, PRI and Userspace IO Page Tables allows an
implementation of DMA Shared Virtual Addressing (vSVA) within a guest.
Dirty tracking enables VM live migration with SRIOV devices and PASID
support allow creating "scalable IOV" devices, among other things.
As these features are fundamental to a VM platform they need to be
uniformly exposed to all the driver families that do DMA into VMs,
which is currently VFIO and VDPA"
For more background, see the extended explanations in Jason's pull request:
https://lore.kernel.org/lkml/Y5dzTU8dlmXTbzoJ@nvidia.com/
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (62 commits)
iommufd: Change the order of MSI setup
iommufd: Improve a few unclear bits of code
iommufd: Fix comment typos
vfio: Move vfio group specific code into group.c
vfio: Refactor dma APIs for emulated devices
vfio: Wrap vfio group module init/clean code into helpers
vfio: Refactor vfio_device open and close
vfio: Make vfio_device_open() truly device specific
vfio: Swap order of vfio_device_container_register() and open_device()
vfio: Set device->group in helper function
vfio: Create wrappers for group register/unregister
vfio: Move the sanity check of the group to vfio_create_group()
vfio: Simplify vfio_create_group()
iommufd: Allow iommufd to supply /dev/vfio/vfio
vfio: Make vfio_container optionally compiled
vfio: Move container related MODULE_ALIAS statements into container.c
vfio-iommufd: Support iommufd for emulated VFIO devices
vfio-iommufd: Support iommufd for physical VFIO devices
vfio-iommufd: Allow iommufd to be used in place of a container fd
vfio: Use IOMMU_CAP_ENFORCE_CACHE_COHERENCY for vfio_file_enforced_coherent()
...
Diffstat (limited to 'drivers/vfio/vfio.h')
-rw-r--r-- | drivers/vfio/vfio.h | 120 |
1 files changed, 114 insertions, 6 deletions
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index bcad54bbab08..2e05418fd18d 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -6,14 +6,25 @@ #ifndef __VFIO_VFIO_H__ #define __VFIO_VFIO_H__ +#include <linux/file.h> #include <linux/device.h> #include <linux/cdev.h> #include <linux/module.h> +struct iommufd_ctx; struct iommu_group; struct vfio_device; struct vfio_container; +void vfio_device_put_registration(struct vfio_device *device); +bool vfio_device_try_get_registration(struct vfio_device *device); +int vfio_device_open(struct vfio_device *device, + struct iommufd_ctx *iommufd, struct kvm *kvm); +void vfio_device_close(struct vfio_device *device, + struct iommufd_ctx *iommufd); + +extern const struct file_operations vfio_device_fops; + enum vfio_group_type { /* * Physical device with IOMMU backing. @@ -54,14 +65,30 @@ struct vfio_group { struct list_head device_list; struct mutex device_lock; struct list_head vfio_next; +#if IS_ENABLED(CONFIG_VFIO_CONTAINER) struct list_head container_next; +#endif enum vfio_group_type type; struct mutex group_lock; struct kvm *kvm; struct file *opened_file; struct blocking_notifier_head notifier; + struct iommufd_ctx *iommufd; }; +int vfio_device_set_group(struct vfio_device *device, + enum vfio_group_type type); +void vfio_device_remove_group(struct vfio_device *device); +void vfio_device_group_register(struct vfio_device *device); +void vfio_device_group_unregister(struct vfio_device *device); +int vfio_device_group_use_iommu(struct vfio_device *device); +void vfio_device_group_unuse_iommu(struct vfio_device *device); +void vfio_device_group_close(struct vfio_device *device); +bool vfio_device_has_container(struct vfio_device *device); +int __init vfio_group_init(void); +void vfio_group_cleanup(void); + +#if IS_ENABLED(CONFIG_VFIO_CONTAINER) /* events for the backend driver notify callback */ enum vfio_iommu_notify_type { VFIO_IOMMU_CONTAINER_CLOSE = 0, @@ -109,20 +136,101 @@ struct vfio_iommu_driver { int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops); -bool vfio_assert_device_open(struct vfio_device *device); - struct vfio_container *vfio_container_from_file(struct file *filep); -int vfio_device_assign_container(struct vfio_device *device); -void vfio_device_unassign_container(struct vfio_device *device); +int vfio_group_use_container(struct vfio_group *group); +void vfio_group_unuse_container(struct vfio_group *group); int vfio_container_attach_group(struct vfio_container *container, struct vfio_group *group); void vfio_group_detach_container(struct vfio_group *group); void vfio_device_container_register(struct vfio_device *device); void vfio_device_container_unregister(struct vfio_device *device); -long vfio_container_ioctl_check_extension(struct vfio_container *container, - unsigned long arg); +int vfio_device_container_pin_pages(struct vfio_device *device, + dma_addr_t iova, int npage, + int prot, struct page **pages); +void vfio_device_container_unpin_pages(struct vfio_device *device, + dma_addr_t iova, int npage); +int vfio_device_container_dma_rw(struct vfio_device *device, + dma_addr_t iova, void *data, + size_t len, bool write); + int __init vfio_container_init(void); void vfio_container_cleanup(void); +#else +static inline struct vfio_container * +vfio_container_from_file(struct file *filep) +{ + return NULL; +} + +static inline int vfio_group_use_container(struct vfio_group *group) +{ + return -EOPNOTSUPP; +} + +static inline void vfio_group_unuse_container(struct vfio_group *group) +{ +} + +static inline int vfio_container_attach_group(struct vfio_container *container, + struct vfio_group *group) +{ + return -EOPNOTSUPP; +} + +static inline void vfio_group_detach_container(struct vfio_group *group) +{ +} + +static inline void vfio_device_container_register(struct vfio_device *device) +{ +} + +static inline void vfio_device_container_unregister(struct vfio_device *device) +{ +} + +static inline int vfio_device_container_pin_pages(struct vfio_device *device, + dma_addr_t iova, int npage, + int prot, struct page **pages) +{ + return -EOPNOTSUPP; +} + +static inline void vfio_device_container_unpin_pages(struct vfio_device *device, + dma_addr_t iova, int npage) +{ +} + +static inline int vfio_device_container_dma_rw(struct vfio_device *device, + dma_addr_t iova, void *data, + size_t len, bool write) +{ + return -EOPNOTSUPP; +} + +static inline int vfio_container_init(void) +{ + return 0; +} +static inline void vfio_container_cleanup(void) +{ +} +#endif + +#if IS_ENABLED(CONFIG_IOMMUFD) +int vfio_iommufd_bind(struct vfio_device *device, struct iommufd_ctx *ictx); +void vfio_iommufd_unbind(struct vfio_device *device); +#else +static inline int vfio_iommufd_bind(struct vfio_device *device, + struct iommufd_ctx *ictx) +{ + return -EOPNOTSUPP; +} + +static inline void vfio_iommufd_unbind(struct vfio_device *device) +{ +} +#endif #ifdef CONFIG_VFIO_NOIOMMU extern bool vfio_noiommu __read_mostly; |